[LARTC] Re: More on qdiscs - about dangling backlogs

[Martin Devera <devik@cdi.cz>]

On Thu, 9 May 2002, Don Cohen wrote:

>  > It should be handled in the same way as requeue only should not increase
>  > stats.
> I guess you mean requeue should be the same as enqueue.

err of course, yes

>  > > I still think it's reasonable to check only at dequeue.  Basically if
>  > > you know max time between dequeues is t, then a queue filled by a
>  > > flood can only remain full for time t + expire_time after the flood
>  > > ends.  After that there will be a dequeue that throws out all the
>  > > flood packets.  Then your next packet will be accepted and delayed at
>  > > most expire_time.
>  >
>  > It might be. Why don't you try it ? I feel still the same about it: I
>  > think that experiment is the only way to test the idea.
>
> What experiments would you like to see?

Implement your idea and measure difference in delay, jitter, thoughtput of
TCP and reaction to flooding.
In other words show that your idea can do better that current approach.
When I was speking about idea like HTB nobody listened. I've to implement
it ..
devik

_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/